The Toyota Research Institute (TRI) has developed a new approach to teach robots dexterous skills, the Toyota Motor Corp. (TMC) subsidiary announced. According to TRI, the generative-AI approach based on diffusion policy is a step toward building "large behavior models (LBMs)" for robots, analogous to the large-language models (LLMs) of conversational AI.
"Our research in robotics is aimed at amplifying people rather than replacing them," says Gill Pratt, CEO of TRI and chief scientist for TMC. "This new teaching technique is both very efficient and produces very high performing behaviors, enabling robots to much more effectively amplify people in many ways."
Previous techniques to teach robots new behaviors were slow, inconsistent, inefficient and often limited to narrowly defined tasks performed in highly constrained environments, TRI says. Roboticists needed to spend many hours writing sophisticated code and/or using numerous trial and error cycles to program behaviors.
TRI says it has already taught robots more than 60 skills using the new approach, including pouring liquids, using tools and manipulating deformable objects. These achievements were realized without writing a single line of new code, but rather by supplying the robot with new data. TRI has set a target of teaching hundreds of new skills by the end of the year and 1,000 by the end of 2024.
"The tasks that I'm watching these robots perform are simply amazing – even one year ago, I would not have predicted that we were close to this level of diverse dexterity," says Russ Tedrake, vice president of Robotics Research at TRI. "What is so exciting about this new approach is the rate and reliability with which we can add new skills. Because these skills work directly from camera images and tactile sensing, using only learned representations, they are able to perform well even on tasks that involve deformable objects, cloth and liquids — all of which have traditionally been extremely difficult for robots."
Connect With Us
